Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnlyHint and openWorldHint, and the description adds substantial context beyond them: chunked return format, a 20,000-character default chunk, a 100,000-character free window, and the presence of a paid upgrade link. Practical constraints (no JS-only pages, no whole-site crawling) are disclosed as behavioral boundaries.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences, zero filler: purpose and format first, then usage routing, then the chunking mechanics. Every sentence carries information the agent needs to call the tool correctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries return-format burden and does so (Markdown, chunked, defaults, free window), and annotations cover the safety profile. It remains silent on failure modes (non-public URLs, blocked pages) and any authentication expectations, which for an open-world fetch tool would be useful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only 'url' is documented), so the description must compensate. It meaningfully explains start_index ('reads later chunks within the free 100,000-character window') and restates the default chunk size, but max_chars is never mentioned and the free-window bound is only implied against start_index's 99999 maximum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource combination ('Returns a public page or PDF as Markdown') and specifies the output shape (chunked Markdown). It also distinguishes itself from a paid sibling ('the linked paid tool') for crawling, so an agent can tell it apart from alternatives without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger ('Use when an agent needs one URL's readable text') and explicit exclusions ('Not for JavaScript-only pages or crawling whole sites'), plus the redirect to the paid alternative. This is the full when/when-not/alternative pattern.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.